activity
20242026
collaborators

11 papers

cs.CV2026

Unified Video Dense Prediction from Disjoint Data

Yihong Sun, Seoung Wug Oh, Jiahui Huang +2

Scene understanding requires simultaneous prediction about geometry, appearance, and semantics. However, existing task-specific annotations are fragmented across incompatible, doma…

cs.CV2026

DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation

Tuan Duc Ngo, Jiahui Huang, Seoung Wug Oh +4

Estimating accurate, view-consistent geometry and camera poses from uncalibrated multi-view/video inputs remains challenging - especially at high spatial resolutions and over long…

cs.CV2026

VideoMaMa: Mask-Guided Video Matting via Generative Prior

Sangbeom Lim, Seoung Wug Oh, Jiahui Huang +3

Generalizing video matting models to real-world videos remains a significant challenge due to the scarcity of labeled data. To address this, we present Video Mask-to-Matte Model (V…

cs.CV2025

FRAME: Pre-Training Video Feature Representations via Anticipation and Memory

Sethuraman TV, Savya Khosla, Vignesh Srinivasakumar +5

Dense video prediction tasks, such as object tracking and semantic segmentation, require video encoders that generate temporally consistent, spatially dense features for every fram…

cs.CV2025

Tuning-Free Multi-Event Long Video Generation via Synchronized Coupled Sampling

Subin Kim, Seoung Wug Oh, Jui-Hsien Wang +2

While recent advancements in text-to-video diffusion models enable high-quality short video generation from a single prompt, generating real-world long videos in a single pass rema…

cs.CV2024

Elevating Flow-Guided Video Inpainting with Reference Generation

Suhwan Cho, Seoung Wug Oh, Sangyoun Lee +1

Video inpainting (VI) is a challenging task that requires effective propagation of observable content across frames while simultaneously generating new content not present in the o…